{"id":"https://openalex.org/W4408355290","doi":"https://doi.org/10.1109/icassp49660.2025.10888928","title":"Improving Acoustic Scene Classification in Low-Resource Conditions","display_name":"Improving Acoustic Scene Classification in Low-Resource Conditions","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355290","doi":"https://doi.org/10.1109/icassp49660.2025.10888928"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I118574674","display_name":"Jiangsu Normal University","ror":"https://ror.org/051hvcm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I118574674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Chen","raw_affiliation_strings":["Jiangsu Normal University,Xuzhou,China,221116"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu Normal University,Xuzhou,China,221116","institution_ids":["https://openalex.org/I118574674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101472223","display_name":"Yunfei Shao","orcid":"https://orcid.org/0000-0003-2311-1670"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun-Fei Shao","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002618865","display_name":"Yong Ma","orcid":"https://orcid.org/0000-0002-1116-0662"},"institutions":[{"id":"https://openalex.org/I118574674","display_name":"Jiangsu Normal University","ror":"https://ror.org/051hvcm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I118574674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Ma","raw_affiliation_strings":["Jiangsu Normal University,Xuzhou,China,221116"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu Normal University,Xuzhou,China,221116","institution_ids":["https://openalex.org/I118574674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111156218","display_name":"Mingsheng Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I118574674","display_name":"Jiangsu Normal University","ror":"https://ror.org/051hvcm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I118574674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingsheng Wei","raw_affiliation_strings":["Jiangsu Normal University,Xuzhou,China,221116"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu Normal University,Xuzhou,China,221116","institution_ids":["https://openalex.org/I118574674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101179818","display_name":"Le Zhang","orcid":"https://orcid.org/0009-0000-8383-9650"},"institutions":[{"id":"https://openalex.org/I118574674","display_name":"Jiangsu Normal University","ror":"https://ror.org/051hvcm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I118574674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Zhang","raw_affiliation_strings":["Jiangsu Normal University,Xuzhou,China,221116"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu Normal University,Xuzhou,China,221116","institution_ids":["https://openalex.org/I118574674"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100692898","display_name":"Weiqiang Zhang","orcid":"https://orcid.org/0000-0001-8820-7812"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.970300018787384,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.970300018787384,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9567000269889832,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.902899980545044,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6720179319381714},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.44778406620025635},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41391295194625854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38843271136283875},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.06578055024147034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6720179319381714},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.44778406620025635},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41391295194625854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38843271136283875},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06578055024147034}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5699999928474426}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1978274651","https://openalex.org/W2194775991","https://openalex.org/W2963163009","https://openalex.org/W2963543871","https://openalex.org/W2987999870","https://openalex.org/W3015530480","https://openalex.org/W3165587897","https://openalex.org/W4282044900","https://openalex.org/W4283693214","https://openalex.org/W4388117483","https://openalex.org/W4390571032","https://openalex.org/W6674316043","https://openalex.org/W6697028695","https://openalex.org/W6754344008","https://openalex.org/W6779341498","https://openalex.org/W6780496662","https://openalex.org/W6789380839","https://openalex.org/W6839321029","https://openalex.org/W6959838169"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Acoustic":[0],"Scene":[1],"Classification":[2],"(ASC)":[3],"identifies":[4],"an":[5,9],"environment":[6],"based":[7],"on":[8,86],"audio":[10],"signal.":[11],"This":[12],"paper":[13],"explores":[14],"ASC":[15],"in":[16,120],"low-resource":[17],"conditions":[18],"and":[19,41,47,59,69,103,123],"proposes":[20],"a":[21,37,92],"novel":[22],"model,":[23],"DS-FlexiNet,":[24],"which":[25],"combines":[26],"depthwise":[27,104],"separable":[28,105],"convolutions":[29,106],"from":[30,79],"MobileNetV2":[31],"with":[32],"ResNet-inspired":[33],"residual":[34],"connections":[35],"for":[36,56],"balance":[38],"of":[39],"efficiency":[40],"accuracy.":[42],"To":[43],"address":[44],"hardware":[45],"limitations":[46],"device":[48],"heterogeneity,":[49],"DS-FlexiNet":[50,118],"employs":[51],"Quantization":[52],"Aware":[53],"Training":[54],"(QAT)":[55],"model":[57],"compression":[58],"data":[60],"augmentation":[61],"methods":[62],"like":[63],"Auto":[64],"Device":[65],"Impulse":[66],"Response":[67],"(ADIR)":[68],"Freq-MixStyle":[70],"(FMS)":[71],"to":[72,97],"improve":[73],"cross-device":[74],"generalization.":[75],"Knowledge":[76],"Distillation":[77],"(KD)":[78],"twelve":[80],"teacher":[81],"models":[82],"further":[83],"enhances":[84],"performance":[85,124],"unseen":[87],"devices.":[88],"The":[89],"architecture":[90],"includes":[91],"custom":[93],"Residual":[94],"Normalization":[95],"layer":[96],"handle":[98],"domain":[99],"differences":[100],"across":[101],"devices,":[102],"reduce":[107],"computational":[108],"overhead":[109],"without":[110],"sacrificing":[111],"feature":[112],"representation.":[113],"Experimental":[114],"results":[115],"show":[116],"that":[117],"excels":[119],"both":[121],"adaptability":[122],"under":[125],"resource-constrained":[126],"conditions.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
